Choosing between man- and zone coverage is one of the most important strategic decisions a defensive coordinator has to make prior to each offensive play in American football. While opposing offensive coordinators and quarterbacks try to identify these defensive strategies visually, the rise of tracking data provides another opportunity to infer the hidden defensive tactics.
Previous approaches attempted to predict zone- or man coverage. One example can be seen in the below screenshot which displays a snapshot from the Amazon Prime broadcast of the week 12 match between the Pittsburgh Steelers and Cleveland Browns of the current NFL season, including a prediction by Amazon’s NFL Next Gen Stats model whether man- or zone coverage will be played. Although the full model and its details are not public, the live broadcast prediction mostly focuses on specific plays without any pre-snap motion. We proceeed similarly, however, in this project, we do not stop there. In contrast, we also depict player movements before the snap, i.e. pre-snap motion, and exploit this additional information using hidden Markov models (HMMs). By modeling the trajectories of defenders depending on hidden states, which represent the offensive players, we infer probabilities for each offensive player being guarded by the specific defenders in every instance of a play that contains player movements. We map this high-dimensional time series information to a single number for each play by calculating the entropy, thus, ending up with a measure of the degree of uncertainty. Incorporating this information into the existing pre-motion model, we can show that the AUC and the detection accuracy are increased. In this way, we provide a data-driven framework that is able to assess the efficiency of pre-snap motion to reveal the defensive strategy, enabling real-time tactical insights for coaches.
We analyze tracking data from nine weeks of the NFL 2022 season, provided by the NFL Big Data Bowl 2024. Beside the tracking data, we also use information on plays and players. We further considered the corresponding data from PFF that assigned the categories , and representing the different schemes to each play. As it is not properly described what means, we omit every play that is associated with this value. Moreover, we omit plays with more than five offensive linemen and with two quarterbacks and those plays that did not contain any pre-snap motion. Then, we end up with XY offensive plays in total, from which the defense played Y in zone and X in man coverage.
Within these plays, we concentrate on the tracking data after the line has been set (because we are not interested in how players come out of the huddle) and before the ball has been snapped by the Center.
To accurately forecast the defensive scheme (man- or zone defense) for every play, we need to create various features derived from the tracking data. In particular, we conducted the following feature engineering steps: ROBERT
Our analysis comprises different steps:
We train different model (LASSO, Random Forest, XGBoost) to predict whether the defense plays a man- or zone coverage scheme. In particular, …..
The model uses the previously described features, blablabla.
ROBERT
We model the movements of defensive players during the phase of pre-snap motion within a hidden Markov framework, in which the underlying states represent the offensive players to be guarded (see Franks et al. 2015 for a similar approach in basketball).
OLE
The following video displays a touchdown from the Kansas City Chiefs against the Arizona Cardinals in Week 1 of the 2022 NFL season. We can see that, pre-snap, Mecole Hardman (KC #17) is in motion. He is immediately followed by the defender Marco Wilson (AZ #20), which is a clear indication for man-coverage.